Abstract
The paper investigates the possibility to extract meaningful information out of natural language design conversation. This meaningful information, referred in this paper as features, represents possible design changes and solutions discussed during collaborative design sessions. Without relying on user input and without disrupting the natural course of the conversations, we envision an automatic implementation of these changes and solutions into a parametric model. The aim of such a system is to allow for an automatic design space exploration without interrupting the design sessions. In this direction, the paper employs mixed research methods which make use of quantitative and qualitative analysis. The results obtained indicate the possibility of extracting structured information to perform changes in various parametric models automatically. The paper also provides discussions around specific limitations, such as unclear precedents due to multimodality input.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
